PhD defence

Sentinel animals enriching artificial intelligence with wildlife ecology to guard rhinos

PhD candidate dr. JAJ (Jasper) Eikelboom MSc MA
Promotor prof.dr. HHT (Herbert) Prins F (Frank) van Langevelde
Co-promotor HJ (Henjo) de Knegt
External copromotor prof. dr A Doelman
Organisation Wageningen University, Wildlife Ecology and Conservation

Mon 28 June 2021 13:30 to 15:00



The survival of both African rhinoceros species is under threat due to large-scale poaching. Therefore I aimed to develop a poacher early warning system that provides conservation officers with more situational awareness. For this task I focused on developing a ''sentinel-based poacher early warning system'', for which I envision nature reserves where abundant prey animals are tracked and where the movement responses of these animals are automatically used to detect the presence and infer the location of poachers. My thesis brings together a number of coherent papers about wildlife conservation, movement ecology and artificial intelligence, aimed at investigating the necessity, analytics and applicability of a sentinel-based poacher early warning system. First, I concluded through an integrative literature review about rhino horn trade legalization that legalizing rhino horn trade will likely negatively impact the remaining wild rhino populations. To preserve rhino species I suggest to combine long- and short-term conservation approaches, prioritizing first the increase of rhino populations within well-protected 'safe havens'. Second, I estimated through a systematic review and a mixed effects meta-analysis that tropical mammal abundances on average declined by 83% and bird abundances by 58% in hunted compared with unhunted areas. My results signify that the impact of hunting on both the abundance and distribution of tropical animals in general is very large and that gazettement of protected areas seems insufficient to safeguard wildlife populations if not accompanied with improved reserve management, effective law enforcement and on-ground protection efforts. Third, I found through an agent-based simulation model with individual movement rules driven only by fear and resources that the coefficient of variation of group size generally lied between 50 and 150% in these simulations, depending on both animal density and the resource scarcity/predation trade-off. Given that the variations of group size are already this large in homogeneous and deterministic scenarios, I consider group size an imprecise collective movement proxy for environmental conditions and can likely only be informative for slowly-evolving environmental conditions with information about the recent history of the animal group. Fourth, I demonstrated through extensive feature engineering and machine learning on cow movement sensor data that it is possible to quantify environmental influence on animal movement with the performance metrics of machine learning regression algorithms. Even though the aim of this framework is to quantify the exact contribution of separate environmental variables on the total variation in animal movement, the core of this framework can be used to accurately predict environmental variation from animal movement as well. Fifth, I algorithmically detected and localized poachers in Welgevonden Game Reserve (South Africa) using animal movement data from 138 savanna ungulates combined with experimentally staged human intrusions. I demonstrated the importance of interpreting animal movement as deviations from expectations given recent movement history and similar environmental conditions, given the complex relationship between the animals' heterogeneous environment and movement. I achieved an average precision of 46% to classify animal movement responses to humans versus all other movement; I distinguished periods with humans present in the area from periods without humans with 86% accuracy in a balanced validation design; and localized these humans with less than 500m error in 54.2% of the experimentally staged poaching intrusions. This chapter thus demonstrates the feasibility of the main theme of this thesis, namely to use a sentinel-based poacher early warning system to detect and localize poachers. Sixth, I demonstrated through deep learning of aerial images from wildlife surveys that semi-automatic aerial animal counts can improve the precision and accuracy of animal population estimates and that automated animal detections from aerial images have the potential to find more animals than humans can. I thus acknowledge the potential of aerial imagery to supplement en masse tracking with sensor tags, but expect animal tracking with cameras to be only suitable for relatively small areas. Finally, in my synthesis I argued that the applicability of my developed sentinel-based poacher early warning system lies mainly in the aid it can provide to short-term wildlife protection efforts during the Anthropocene, which can concurrently reduce some of the negative effects associated with 'militarized conservation' (e.g., human rights violations). I also forecasted a large role for artificial intelligence in wildlife ecology research, which may drastically change the way scientific understanding is acquired in the near future.